© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Llama3.3-70B-IT
    5. 50-RESID-POST-GF
    7. 59509
    Prev
    Next
    INDEX
    Explanations

    asteroid words

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.3-70B-IT @ 50-resid-post-gf
    Configuration
    Goodfire/Llama-3.3-70B-Instruct-SAE-l50/Llama-3.3-70B-Instruct-SAE-l50.pt
    Prompts (Dashboard)
    10,000 prompts, 128 tokens each
    Dataset (Dashboard)
    lmsys/lmsys-chat-1m
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    sh
    -0.15
    son
    -0.13
    soft
    -0.12
    y
    -0.12
    spy
    -0.12
    ss
    -0.12
    sg
    -0.12
    set
    -0.11
    n
    -0.11
    sm
    -0.11
    POSITIVE LOGITS
    er
    0.16
    prise
    0.14
    apeut
    0.14
    iors
    0.14
    ior
    0.14
    restrial
    0.13
    preter
    0.13
    eri
    0.13
    rible
    0.12
    olem
    0.12
    Activations Density 0.071%

    No Known Activations